metadata
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: DINO Model (model_idx_0910)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 910 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9483 |
| Val Accuracy | 0.8333 |
| Test Accuracy | 0.8324 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
clock, bridge, dinosaur, possum, road, telephone, lion, wolf, bottle, couch, flatfish, can, television, pickup_truck, oak_tree, cup, sweet_pepper, caterpillar, house, forest, elephant, motorcycle, dolphin, pear, woman, bee, squirrel, plain, pine_tree, leopard, crocodile, chair, boy, orange, mushroom, snail, castle, lamp, willow_tree, girl, keyboard, mouse, raccoon, tulip, porcupine, rabbit, cloud, man, trout, camel